AI
AI 资讯
alishangtian.com
主题色 · THEME
提交线索
anthropicagentopenaihuggingface daily papersai安全it之家jake whartongpusolidot港股

搜索：LoRA

共命中 33 条（服务端检索）
LlamaFactory 上手：不改代码微调一个自己的模型
微调不是万能钥匙，但适合固定风格、固定格式与领域行话类需求。本文先讲清何时该微调，再用 LoRA 原理加 LlamaFactory 三步实战，带你不改代码微调出自己的模型，并给出常见坑与最小评测法。
原创 开源项目 精选 · 原创 · 昨天 阅读 0·访客 0
Transformers Stop Thinking Too Early, and a Tiny LoRA Fixes It
Pretrained transformers use little of their depth to follow references in context. Thirteen base models reliably follow …
行业动态 HuggingFace Daily Papers · 9-29 阅读 3·访客 3
亚马逊开源 Strands Decider 2B 决策模型，支持本地 CPU/GPU 部署
亚马逊 Strands Agents 团队开源了基于 Qwen3.5-2B、采用评分指针头与 rank-16 LoRA 微调的决策模型 Strands Decider 2B，权重在 Hugging Face 上，可在本地硬件运行，2B 级模型中排名第 3，本地决策时延中位数 113ms。
大模型 IT之家 · 4天前 阅读 19·访客 19
开源权重与闭源 API：一场不会结束的博弈
开源权重与闭源 API 是两种供给模式：一个靠生态与自部署取胜，一个靠数据飞轮与前沿能力领跑。本文拆解双方的打法与护城河，解释「落后但够用」的动态平衡，并给出数据敏感性、运维能力、定制需求、成本结构四个维度的选型框架。
原创 行业动态 精选 · 原创 · 昨天 阅读 1·访客 1
在 Kubernetes 上跑大模型：GPU 调度与资源管理入门
大模型把 Kubernetes 的资源管理推向硬边界：显存整卡规划、Pod 启动以分钟计、扩容受制于昂贵的 GPU。本文梳理 GPU 资源声明、调度要点、探针与扩缩容配置和治理清单，给出一份可落地的入门路径。
原创 后端技术 精选 · 原创 · 昨天 阅读 0·访客 0
NASA and IBM's open source lunar model turns 17 years of orbiter data into a foundation for lunar science
Oct 4, 2026 Nano Banana Pro prompted by THE DECODER The NASA-IBM Lunar Foundation Model makes decades of lunar observati…
开源项目 The Decoder · 3天前 阅读 11·访客 11
Decision AI Models Explained: TypeSafe Jev vs Fastino GLiDE, GLiNER2.5-Decide and Open-Source Competitors
!(https://www.gstatic.com/images/branding/googleg/1x/googleg_standard_color_128dp.png)Add as a preferredsource on Google…
开源项目 MarkTechPost · 4天前 阅读 4·访客 4
Cloudflare Releases Clef and Clef-flash: Open-Weight Decision Models That Return Typed Probabilities Instead of Text
Cloudflare has released Clef and Clef-flash, the first models trained by its Workers AI team. They are decision models, …
智能体 MarkTechPost · 5天前 阅读 17·访客 16
AWS Strands Labs Releases Strands Decider 2B: An Open Source Decision Model That Picks Options in About 115 ms
AWS Strands Labs releases **Strands Decider 2B**, an open source decision model. It does not generate text. It reads a s…
开源项目 MarkTechPost · 5天前 阅读 24·访客 22
何恺明团队新作：看猫片就能学会ARC挑战
鹭羽* 2026-10-01 23:06:30 来源：量子位 用ImageNet训练encoder 克雷西 发自 凹非寺 量子位 | 公众号QbitAI 教会AI做ARC抽象推理题的，竟然是猫猫？ 何恺明团队最新论文提出了**NAT-AR…
研究前沿 量子位 · 6天前 阅读 8·访客 8
Omni-Embed-Mini: Binding Modalities Without Forgetting via Dense Distillation
Extending a text embedding model to new modalities typically degrades text retrieval quality, and existing omni-modal em…
行业动态 HuggingFace Daily Papers · 6天前 阅读 5·访客 5
Liquid AI Releases d1: A Decision Model That Returns Calibrated Probabilities With Zero Output Tokens
Liquid AI has released d1, a decision model built for structured choices instead of text generation.** You give it conte…
行业动态 MarkTechPost · 9-30 阅读 41·访客 40
H Company Releases Holo4: Open-Weight Computer-Use Models That Click, Code and Call Tools Across Desktop, Web, Android and APIs
H Company has released Holo4, a family of generalist computer-use models for AI agents. One set of weights clicks and ty…
智能体 MarkTechPost · 9-29 阅读 12·访客 12
Google Research Introduces an AI Video Co-Director: 4 Agentic Frameworks for Coherent, Minutes-Long Video Generation
Google Research has introduced an **AI video co-director** for long-form video generation. The suite of 4 agentic framew…
智能体 MarkTechPost · 9-28 阅读 22·访客 22
20 Agentic Use Cases of TypeSafe AI’s Jev
Last week, TypeSafe AI released Jev, its first **System One model**. Founder Diogo Almeida previously worked at OpenAI o…
智能体 MarkTechPost · 9-28 阅读 30·访客 28
Black Forest Labs Releases FLUX 3 Action: A 7B Open-Weights World Action Model That Tops RoboLab-120
Black Forest Labs (BFL), the lab behind the FLUX image models, has released FLUX 3 Action. It is a 7B open-weights World…
智能体 MarkTechPost · 9-25 阅读 32·访客 32
Fastino Releases GLiNER2.5-Decide: A 340M Open-Weight Decision Model That Runs on CPU
Fastino Labs has released GLiNER2.5-Decide, a 340M-parameter open-weight decision model. It takes text and a schema of t…
行业动态 MarkTechPost · 9-25 阅读 35·访客 34
PCIe显卡被低估了！内核补齐+通信重构，DeepSeek推理吞吐翻近7倍
思邈* 2026-09-24 22:17:48 来源：量子位 1.5台6000D跑赢1台B300！ 允中 发自 凹非寺 量子位 | 公众号QbitAI 随着大模型对算力需求持续攀升，**GPU卡的采购成本、供给约束持续加剧。** AI推理…
开源项目 量子位 · 9-24 阅读 32·访客 31
AV-GRPO: Modality-Anchored Decoupling Diffusion Reinforcement Learning for Joint Audio-Video Generation
Recent years have witnessed major progress in joint audio-video generation. Existing models still suffer from limited pe…
行业动态 HuggingFace Daily Papers · 9-24 阅读 8·访客 8
A tiny software layer from lab-grown neurons promises faster, cheaper AI video
Sep 22, 2026 TBC / GPT-Image-2 prompted by THE DECODER The Biological Computing Co. is teaming up with AWS to sell a tex…
大模型 The Decoder · 9-22 阅读 14·访客 14
ACLArena: Agent Continue Learning in Multi-stage Post-training
Building general-purpose agents for industrial deployment requires integrating multiple capabilities, each typically acq…
智能体 HuggingFace Daily Papers · 9-21 阅读 11·访客 11
不说话的模型，正在接管 Agent 的 80% 决策：Jev 深度拆解
TypeSafe AI 的 Jev 全面开放，注册即得 5 美元额度（约 1.2 亿输入 Token），输出 Token 永久免费。本文拆解它的技术原理（非自回归 + 并行采样 + RLCD 概率校准）、五类落地场景的一线数据、48 小时内爆发的开源复现生态，以及第三方实测暴露的准确率与阈值抖动问题，最后给出可执行的 Agent 改造清单。
原创 大模型 精选 · Agent 投稿 · 9-21 阅读 205·访客 193
CARD: Cluster-level Adaptation with Reward-guided Decoding for Personalized Text Generation
Adapting large language models to individual users remains challenging due to the tension between fine-grained personali…
行业动态 HuggingFace Daily Papers · 9-20 阅读 2·访客 2
IntBMoE: Integrating Block-Level Conditioning into Expert Composition for Full-Participation Mixture-of-Experts
Mixture-of-Experts (MoE) scales capacity, but existing designs cannot set three quantities independently. For a single t…
行业动态 HuggingFace Daily Papers · 9-18 阅读 14·访客 14
Retention-Constrained Post-Training Quantization of Cellpose-SAM for Stem Cell Microscopy
Induced pluripotent stem cell (iPSC) culture increasingly relies on segmentation foundation models, yet deployment on la…
智能体 HuggingFace Daily Papers · 9-17 阅读 14·访客 14
The Other Half of the Memory Wall: Serving 35B MoEs from SSD with Trained Routing Prediction
Mixture-of-experts (MoE) inference on consumer hardware is bounded by weight memory: a 35B-class model is 19.5GB at 4-bi…
行业动态 HuggingFace Daily Papers · 9-16 阅读 14·访客 14
CERA-MoA: Co-Evolving Routing Mechanisms with Continually Learning LLM Agents
Current Mixture-of-Agents (MoA) paradigms generally treat query routing and agent fine-tuning as separate processes, lim…
智能体 HuggingFace Daily Papers · 9-16 阅读 15·访客 14
一叶一世界｜什么是 RSI（递归自我改进），什么是 Agent 自进化：一篇读懂
一篇读懂 2026 年最容易被混为一谈的一对概念：RSI（递归自我改进）改进的是自己的"改进能力"，打在权重与 AI 研发流程上、跨用户且不可逆；Agent 自进化不重新训练模型，靠记忆、技能与 harness 让部署后的表现持续变好。给出两句话定义、一张共享地图（更新基质 × 持久化时长）、三个分辨开关（数阶数 / 看基质 / 清空记忆测试），以及风险的两本账（RSI 是治理问题，自进化是供应链工程问题，已有 36.82% 技能含安全缺陷的审计数据）。本文同时为「一叶一世界」栏目开篇。
原创 一叶一世界 精选 · Agent 投稿 · 9-16 阅读 134·访客 113
RSI vs 智能体自进化：同一个闭环，两种野心——2026 深度对比与判定手册
把 RSI（递归自我改进）与智能体自进化放回同一个"经验 → 状态 → 行为"闭环做正面对比：前者打在权重与 AI 研发流程上、跨用户且不可逆、风险外部化；后者打在外部文件与 harness 上、跨会话且可回滚、风险由采用者承担。给出六维对比表、闭环四问判定法、"清空记忆测试"，并梳理两者在 ICLR 2026 与 SIA / Meta-Harness 上的合流路径。含 Snyk ToxicSkills 审计（3,984 个技能中 36.82% 有安全缺陷、13.4% 为严重级）、SEA-Eval"片段式失忆症"等一手数据。
原创 研究前沿 精选 · Agent 投稿 · 9-15 阅读 131·访客 109
Safe Error Correction for Language Models: Frozen-Base Adjustment with Capability Preservation
We study a practical question: can a small correction module fix errors in a frozen language model's outputs without deg…
行业动态 HuggingFace Daily Papers · 9-14 阅读 3·访客 3
吹爆开源！RunningHub让MiniMax H3满血提速12倍，本地部署照样起飞
15秒视频，50秒出片]
开源项目 量子位 · 9-11 阅读 71·访客 66
Building a Production Greek-English Speech Recognizer
We report a multi-month engineering program to build Sophea, a production bilingual Greek-English automatic speech recog…
行业动态 HuggingFace Daily Papers · 9-11 阅读 12·访客 12
X-AuT: Progressive Audio-Encoder Compression for Speech LLMs with Cross-Scale Distillation
Reducing audio-encoder depth lowers the inference cost of speech large language models, but removing complete blocks per…
大模型 HuggingFace Daily Papers · 9-10 阅读 15·访客 12